Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Desko77/claude-code-skills-1cWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/desko77/claude-code-skills-1c/docx-to-md)<a href="https://agentmods.dev/commands/desko77/claude-code-skills-1c/docx-to-md"><img src="https://agentmods.dev/badge/commands/desko77/claude-code-skills-1c/docx-to-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/desko77/claude-code-skills-1c/docx-to-md"><img src="https://agentmods.dev/badge/commands/desko77/claude-code-skills-1c/docx-to-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00522 |
| Opus 5 | $0.00000 | $0.00261 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
docx-to-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- docx-to-md — 100% identical, 0 lines differ
What it actually says
Конвертируй DOCX-файл в Markdown.
Путь к файлу: $ARGUMENTS
Скрипт (всю работу делает локально, токены модели не тратит):
python ~/.claude/scripts/docx_to_md.py "$ARGUMENTS"
Если в документе есть картинки, они будут извлечены в папку images/ рядом с MD-файлом. Если путь к файлу не указан - спроси у пользователя.
Как запускать (по стоимости токенов)
Скрипт бесплатен. Платный только контекст сессии: на каждый ход агента он пересылается модели целиком, поэтому в нагруженной сессии даже тривиальный запуск обходится дорого. Выбирай способ по тому, нужен ли результат агенту дальше.
-
Содержимое результата агенту НЕ нужно (цель - просто получить .md файл):
- Запусти скрипт, сообщи путь к результату и число блоков. Содержимое MD в контекст НЕ читай.
- Еще дешевле - не вызывать эту команду вообще, а запустить скрипт напрямую через префикс
!(0 токенов модели):!python ~/.claude/scripts/docx_to_md.py "путь\файл.docx" - Если сессия уже нагружена, предложи пользователю этот прямой вариант.
-
Содержимое нужно для дальнейшей работы И сессия уже нагружена (большой контекст):
- Делегируй субагенту на Haiku (Agent/Task, model: haiku): пусть запустит скрипт, прочитает MD и вернет то, что реально нужно дальше.
- Нужна выжимка, структура или ответ по документу -> субагент вернет компактно, большой MD не попадет в основной контекст. Это экономит.
- Нужен ПОЛНЫЙ сырой текст MD в основном контексте -> субагент не экономит (текст все равно придет сюда) и добавит оверхед. Тогда прочитай файл напрямую, без субагента.
-
Сессия легкая (контекст небольшой): просто запусти скрипт inline и работай с результатом как обычно - городить субагента смысла нет.
После конвертации сообщи путь к результату и число блоков.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 29 lines · 0 tokens per session scan A 9301a6d92b36
docx-to-md is a command published in the GitHub repository Desko77/claude-code-skills-1c (60 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
docx-to-md
A command that converts a DOCX file, the common Microsoft Word document format, into a Markdown text file. It also extracts pictures into an images folder beside the result.
move-project
A command for moving a project to another folder while preserving its Claude Code memory, sessions, and plans. It also accounts for how Claude Code maps project paths to its memory folders.
check-uuid
A command recipe for checking whether UUIDs, unique identifiers, are duplicated in 1C MDO files. It can inspect a chosen path or the project’s source folder and optionally fix duplicates.
browser-debug
A command recipe for starting Yandex Browser with remote debugging enabled through the Chrome DevTools Protocol, a browser control and inspection interface. It also checks whether the debugging connection is available.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.